© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13000
    Prev
    Next
    INDEX
    Explanations

    categories including examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vÄįetnÄĽ
    -0.12
    including
    -0.10
    cca
    -0.10
    åĮħæĭ¬
    -0.10
    Including
    -0.10
    ASF
    -0.10
     including
    -0.10
     instead
    -0.09
    adi
    -0.09
    iry
    -0.09
    POSITIVE LOGITS
     ones
    0.17
     lẫn
    0.15
     Ones
    0.11
    ones
    0.09
    resi
    0.09
     Andrea
    0.09
     olmak
    0.08
    847
    0.08
    353
    0.08
    oles
    0.08
    Activations Density 0.163%

    No Known Activations